BUG: fixed line terminator behavior on Windows

* related issue: pandas-dev#20353

Author: deflatSOCO

pandas/io/common.py

@@ -4,6 +4,7 @@
 import csv
 import codecs
 import mmap
+import io
 from contextlib import contextmanager, closing
 from zipfile import ZipFile
 
@@ -394,13 +395,13 @@ def _get_handle(path_or_buf, mode, encoding=None, compression=None,
     elif is_path:
         if compat.PY2:
             # Python 2
-            f = open(path_or_buf, mode)
+            f = io.open(path_or_buf, mode, newline='\n')
         elif encoding:
             # Python 3 and encoding
-            f = open(path_or_buf, mode, encoding=encoding)
+            f = open(path_or_buf, mode, encoding=encoding, newline='\n')
         elif is_text:
             # Python 3 and no explicit encoding
-            f = open(path_or_buf, mode, errors='replace')
+            f = open(path_or_buf, mode, errors='replace', newline='\n')
         else:
             # Python 3 and binary mode
             f = open(path_or_buf, mode)

pandas/tests/frame/test_to_csv.py

@@ -871,24 +871,22 @@ def test_to_csv_index_no_leading_comma(self):
         assert buf.getvalue() == expected
 
     def test_to_csv_line_terminators(self):
+        # GH 20353
         df = DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]},
                        index=['one', 'two', 'three'])
 
-        buf = StringIO()
-        df.to_csv(buf, line_terminator='\r\n')
-        expected = (',A,B\r\n'
-                    'one,1,4\r\n'
-                    'two,2,5\r\n'
-                    'three,3,6\r\n')
-        assert buf.getvalue() == expected
+        with ensure_clean() as path:
+            df.to_csv(path, line_terminator='\r\n')
 
-        buf = StringIO()
-        df.to_csv(buf)  # The default line terminator remains \n
-        expected = (',A,B\n'
-                    'one,1,4\n'
-                    'two,2,5\n'
-                    'three,3,6\n')
-        assert buf.getvalue() == expected
+            expected = (b',A,B\r\none,1,4\r\ntwo,2,5\r\nthree,3,6\r\n')
+            with open(path, mode='rb') as f:
+                assert f.read() == expected
+
+            df.to_csv(path)  # The default line terminator remains \n
+
+            expected = (b',A,B\none,1,4\ntwo,2,5\nthree,3,6\n')
+            with open(path, mode='rb') as f:
+                assert f.read() == expected
 
     def test_to_csv_from_csv_categorical(self):
 

pandas/tests/io/formats/test_to_csv.py

@@ -285,3 +285,62 @@ def test_to_csv_string_array_utf8(self):
             df.to_csv(path, encoding='utf-8')
             with open(path, 'r') as f:
                 assert f.read() == expected_utf8
+
+    def test_to_csv_string_with_lf(self):
+        # GH 20353
+        data = {
+            'int': [1, 2, 3],
+            'str_lf': ['abc', 'd\nef', 'g\nh\n\ni']
+        }
+        df = pd.DataFrame(data)
+
+        with tm.ensure_clean('lf_test.csv') as path:
+            expected_bin = \
+                b'int,str_lf\n' \
+                b'1,abc\n' \
+                b'2,"d\nef"\n' \
+                b'3,"g\nh\n\ni"\n'
+
+            df.to_csv(path, index=False)
+            with open(path, 'rb') as f:
+                assert f.read() == expected_bin
+
+            # 'line_terminator' should not change inner element
+            expected_bin = \
+                b'int,str_lf\r\n' \
+                b'1,abc\r\n' \
+                b'2,"d\nef"\r\n' \
+                b'3,"g\nh\n\ni"\r\n'
+
+            df.to_csv(path, line_terminator='\r\n', index=False)
+            with open(path, 'rb') as f:
+                assert f.read() == expected_bin
+
+    def test_to_csv_string_with_crlf(self):
+        # GH 20353
+        data = {
+            'int': [1, 2, 3],
+            'str_crlf': ['abc', 'd\r\nef', 'g\r\nh\r\n\r\ni']
+        }
+        df = pd.DataFrame(data)
+
+        with tm.ensure_clean('crlf_test.csv') as path:
+            expected_bin = \
+                b'int,str_crlf\n' \
+                b'1,abc\n' \
+                b'2,"d\r\nef"\n' \
+                b'3,"g\r\nh\r\n\r\ni"\n'
+
+            df.to_csv(path, index=False)
+            with open(path, 'rb') as f:
+                assert f.read() == expected_bin
+
+            expected_bin = \
+                b'int,str_crlf\r\n' \
+                b'1,abc\r\n' \
+                b'2,"d\r\nef"\r\n' \
+                b'3,"g\r\nh\r\n\r\ni"\r\n'
+
+            df.to_csv(path, line_terminator='\r\n', index=False)
+            with open(path, 'rb') as f:
+                assert f.read() == expected_bin